{"title":"FIRM AUTOMATION: A REINFORCEMENT LEARNING APPROACH","authors":"Ipseeta Nanda, Rajesh De","doi":"10.26480/imcs.02.2022.28.30","DOIUrl":null,"url":null,"abstract":"In most automation, we use ANN or RNN based algorithms. This results well but the prior information is what actions were previously taken by a human, this cannot be the only measure of learning a process we know humans learn everything with experience. And the most appropriate algorithm to learn like a human is Reinforcement Learning","PeriodicalId":292564,"journal":{"name":"INFORMATION MANAGEMENT AND COMPUTER SCIENCE","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"INFORMATION MANAGEMENT AND COMPUTER SCIENCE","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26480/imcs.02.2022.28.30","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In most automation, we use ANN or RNN based algorithms. This results well but the prior information is what actions were previously taken by a human, this cannot be the only measure of learning a process we know humans learn everything with experience. And the most appropriate algorithm to learn like a human is Reinforcement Learning
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
